<dependency> <groupId>net.htmlparser.jericho</groupId> <artifactId>jericho-html</artifactId> <version>3.4</version> </dependency> public String cleanHtml(String html) { Source source = new Source(html); OutputDocument outputDocument = new OutputDocument(source); outputDocument.remove(new ElementFilter("script")); outputDocument.remove(new ElementFilter("style")); for (Element element : source.getAllElements()) { if (!element.getStartTag().getName().equals("a")) { element.getStartTag().removeAttribute("onclick"); element.getStartTag().removeAttribute("class"); } } return outputDocument.toString(); } public static void main(String[] args) { String cleanedHtml = cleanHtml(htmlText); System.out.println(cleanedHtml); }